• 한국IT서비스학회지
• /
• 제19권4호
• /
• pp.1-11
• /
• 2020

Through text mining, sentiment analysis, and semiotics analysis, this study aims to reinterpret the meaning of user emotional words and related words to derive strategic elements of brand and design. After selecting a local car manufacturer whose user opinion on the brand is a clear topic, web-crawl the car comments of the manufacturer directly created by the users online. Then, analyze the extracted morphology and its associated words and convert them to fit the marketing mix theory. Through this process, propose a methodology that allows consumers to supplement and improve brand elements with negative sensibilities, and to inherit elements with positive sensibilities and manage brands reasonably. In particular, the Map presented in this study are considered to be fully utilized as information for overall brand management.

• 산업공학
• /
• 제21권2호
• /
• pp.237-246
• /
• 2008

In today's competitive global environment, technological innovation is an important issue. Many countries are devising national level strategies to further strengthen industrial capacity in support of innovative companies. South Korea is no exception, and multiple strategies are in place to aid innovative development in the private sector. This study postulates that such national level strategies are applied differently depending on the innovation goal pursued by the service sector in Korea. We use data mining methods to test such research hypothesis. Factor analysis is used for clustering of various service companies, while association rule is used in finding the relationship per each cluster. The results show that national level strategies are underutilized and unequally distributed. This may be attributed to the disparity between the demand and needs of the private sector and the opinion of the government, which lead to underutilized and indistinguishable strategies.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2013년도 추계학술발표대회
• /
• pp.1145-1146
• /
• 2013

인터넷과 스마트폰의 발달로 SNS서비스의 사용자와 데이터가 활발하게 증가하고 있다. 이로 인하여 SNS 데이터의 가치와 신뢰성이 점점 증가하고 있으며, 이러한 추세에 따라 여러 연구와 실험을 통하여 데이터를 분석하고 분석 결과를 제공하는 서비스가 증가하고 있다. 본 논문에서는 이러한 배경을 바탕으로 특정 키워드를 포함하고 있는 한글 트윗을 검색하여 해당 트윗에 대한 연관 키워드와 감정 키워드를 분석해서 출력해주는 시스템을 개발한다.

• 산업경영시스템학회지
• /
• 제41권2호
• /
• pp.9-15
• /
• 2018

This study is intended to investigate that it is possible to analyze the public awareness and satisfaction of the weather forecast service provided by the Korea Meteorological Administration (KMA) through social media data as a way to overcome limitations of the questionnaire-based survey in the previous research. Sentiment analysis and association rule mining were used for Twitter data containing opinions about the weather forecast service. As a result of sentiment analysis, the frequency of negative opinions was very high, about 75%, relative to positive opinions because of the nature of public services. The detailed analysis shows that a large portion of users are dissatisfied with precipitation forecast and that it is needed to analyze the two kinds of error types of the precipitation forecast, namely, 'False alarm' and 'Miss' in more detail. Therefore, association rule mining was performed on negative tweets for each of these error types. As a result, it was found that a considerable number of complaints occurred when preventive actions were useless because the forecast predicting rain had a 'False alarm' error. In addition, this study found that people's dissatisfaction increased when they experienced inconveniences due to either unpredictable high winds and heavy rains in summer or severe cold in winter, which were missed by weather forecast. This study suggests that the analysis of social media data can provide detailed information about forecast users' opinion in almost real time, which is impossible through survey or interview.

• 산업경영시스템학회지
• /
• 제41권4호
• /
• pp.131-137
• /
• 2018

People write reviews of numerous products or services on the Internet, in their blogs or community bulletin boards. These unstructured data contain important emotions and opinions about the author's product or service, which can provide important information for future product design or marketing. However, this text-based information cannot be evaluated quantitatively, and thus they are difficult to apply to mathematical models or optimization problems for product design and improvement. Therefore, this study proposes a method to quantitatively extract user's opinion or preference about a specific product or service by utilizing a lot of text-based information existing on the Internet or online. The extracted unstructured text information is decomposed into basic unit words, and positive rate is evaluated by using existing emotional dictionaries and additional lists proposed in this study. This can be a way to effectively utilize unstructured text data, which is being generated and stored in vast quantities, in product or service design. Finally, to verify the effectiveness of the proposed method, a case study was conducted using movie review data retrieved from a portal website. By comparing the positive rates calculated by the proposed framework with user ratings for movies, a guideline on text mining based evaluation of unstructured data is provided.

• ETRI Journal
• /
• 제43권1호
• /
• pp.95-108
• /
• 2021

Application (app) ratings are feedback provided voluntarily by users and serve as important evaluation criteria for apps. However, these ratings can often be biased owing to insufficient or missing votes. Additionally, significant differences have been observed between numeric ratings and user reviews. This study aims to predict the numeric ratings of Google apps using machine learning classifiers. It exploits numeric app ratings provided by users as training data and returns authentic mobile app ratings by analyzing user reviews. An ensemble learning model is proposed for this purpose that considers term frequency/inverse document frequency (TF/IDF) features. Three TF/IDF features, including unigrams, bigrams, and trigrams, were used. The dataset was scraped from the Google Play store, extracting data from 14 different app categories. Biased and unbiased user ratings were discriminated using TextBlob analysis to formulate the ground truth, from which the classifier prediction accuracy was then evaluated. The results demonstrate the high potential for machine learning-based classifiers to predict authentic numeric ratings based on actual user reviews.

• 한국전자거래학회지
• /
• 제18권4호
• /
• pp.315-326
• /
• 2013

소셜 미디어에서는 상품평, 영화평 등의 다양한 종류의 의견이 표현되고 있으며, 사용자들이 물품 구매 등에 있어 이러한 의견을 참고로 하여 결정을 내리는 것은 일반적이 되었다. 하지만 의견 정보의 활용도가 높아질수록 이를 부적절하게 왜곡하는 사례 또한 증가하고 있다. 예를 들어, 홍보를 목적으로 과도하게 긍정적인 의견이 포함된 리뷰를 작성하거나, 반대로 일반적인 평가에서 벗어나 과도하게 부정적인 의견을 게시하는 경우 등이다. 편향된 의견은 소셜 미디어의 신뢰성과 연결 되기 때문에 이를 검출하는 것은 점차 중요한 문제로 대두되고 있다. 기존의 오피니언 마이닝 혹은 감성 분석은 문서를 분석하여 그 문서가 가지고 있는 의견의 성향을 판단하는 기법이다. 하지만 기존의 연구는 의견을 단순히 긍정/부정으로만 분류하는 방향으로 연구가 이루어져 왔으며, 특히 사전에 의견 성향에 따라 분류된 충분한 양의 학습 데이터가 필요하다는 단점이 있다. 본 논문에서는 학습데이터가 없는 경우에, 전체 문서의 의견 성향 분포에서 벗어난 의견 문서를 검출하는 기법을 제안한다. 여기에는 각도기반 이상치 탐지와, 개인화된 페이지랭크 방법을 활용한다. 또한 영화 리뷰 문서를 대상으로 실험을 수행하여 제안한 방법들의 성능을 분석하였다.

• Journal of the Korean Data and Information Science Society
• /
• 제26권6호
• /
• pp.1259-1269
• /
• 2015

최근 빅 데이터는 학계에서 키워드로 자리매김을 하고 있다. 빅 데이터의 유용성은 학계뿐만 아니라 정부, 지자체 그리고 기업체까지 파급되고 있고, 빅 데이터 속에서 유용한 정보를 도출해 내기 위해 노력하고 있다. 본 연구에서는 영화에 대한 리뷰를 가지고 텍스트 마이닝 (text mining)을 이용한 빅 데이터 분석을 수행한다. 본 연구의 목적은 포털 사이트 'D'사와 영화진흥위원회의 영화에 대한 리뷰 데이터, 그리고 고객들의 평점평균 (score)과 스크린 수 (screen number)를 설명변수로 사용하고, 영화 흥행 여부를 종속변수로 하여 로지스틱 회귀분석을 통한 영화 흥행 예측 모형을 제안하는 것이다. 분석결과, 본 연구에서 제안한 예측모형의 정분류율은 95.74%로 얻어졌다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권12호
• /
• pp.3218-3241
• /
• 2023

Financial fraud undermines the sustainable development of financial markets. Financial statements can be regarded as the key source of information to obtain the operating conditions of listed companies. Current research focuses more on mining financial digital data instead of looking into text data. However, text data can reveal emotional information, which is an important basis for detecting financial fraud. The audit opinion of the financial statement is especially the fair opinion of a certified public accountant on the quality of enterprise financial reports. Therefore, this research was carried out by using the data features of 4,153 listed companies' financial annual reports and audits of text opinions in the past six years, and the paper puts forward a financial fraud detection model integrating audit opinions. First, the financial data index database and audit opinion text database were built. Second, digitized audit opinions with deep learning Bert model was employed. Finally, both the extracted audit numerical characteristics and the financial numerical indicators were used as the training data of the LightGBM model. What is worth paying attention to is that the imbalanced distribution of sample labels is also one of the focuses of financial fraud research. To solve this problem, data enhancement and Focal Loss feature learning functions were used in data processing and model training respectively. The experimental results show that compared with the conventional financial fraud detection model, the performance of the proposed model is improved greatly, with Area Under the Curve (AUC) and Accuracy reaching 81.42% and 78.15%, respectively.

• 한국융합학회논문지
• /
• 제8권12호
• /
• pp.265-274
• /
• 2017

본 논문은 빅데이터 분석 교육의 문제점을 고찰해 그 개선 방안을 제시한다. 빅데이터의 특성은 V3에서 V5로 진화하고 있다. 이에 빅데이터 분석 교육도 V5를 감안한 데이터 분석 교육이 되어야 한다. 작금 불확실성의 증대는 데이터 분석의 리스크를 증가시키기에 내적 외적 구조화/비구조화 데이터를 비롯해 교란 요인마저 분석할 때 데이터의 신뢰성은 증가될 수 있다. 그리고 평판분석을 활용할 때 범하기 쉬운 오류가 가변성과 불확실성에 대한 상황 인식이다. 가변성의 측면을 고려해, 다양한 변수와 옵션에 의한 불확실성의 상황을 인식하고 대비한 데이터 분석이 이뤄질 때 데이터에 대한 신뢰성과 정확성은 증가할 수 있다. 사회관계망 분석에서 학생들과 일반 연구자들이 주로 활용하는 것이 텍스톰과 노드엑셀의 노드 분석이다. 사화관계망 분석은 매개중심성에 의한 상황 분석을 통해 다크 데이터를 찾아 이상 현상을 감지하고 현 상황을 분석하여 유용한 의미를 얻고 미래를 예측할 수 있어야 한다.